Project source code

Source Code:

# Load required libraries

suppressWarnings({
 library(tidyverse)
library(ggplot2)
library(plotly)  
library(maps)
library(leaflet)
library(readr)

  library(plotly)
  library(dplyr)
  library(viridis)  

})

# Load necessary libraries
library(dplyr)  # For data manipulation
library(leaflet)  # For creating interactive maps
library(rnaturalearth)  # For world map data

# Load the data (change the path to where your file is stored)
suicide_data <- read.csv("/Users/kiran/Documents/GMU/STAT 515/Mid Project/suicide-rates-all.csv")

# Summarize the data to get the average suicide rate for each country
average_suicide_rate <- suicide_data %>%
  group_by(Country) %>%
  summarise(Average_Suicide_Rate = mean(suscide.rate, na.rm = TRUE), .groups = "drop")  # Add .groups = "drop" to avoid warnings

# Load world map data
world <- ne_countries(scale = "medium", returnclass = "sf")

# Merge world map data with average suicide rates
world_data <- merge(world, average_suicide_rate, by.x = "name", by.y = "Country", all.x = TRUE)

# Create color palette for suicide rates
pal <- colorNumeric(palette = "YlOrRd", domain = world_data$Average_Suicide_Rate, na.color = "transparent")

# Create interactive leaflet map
leaflet(world_data) %>%
  addTiles() %>%
  addPolygons(
    fillColor = ~pal(Average_Suicide_Rate),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "3",
    fillOpacity = 0.7,
    highlight = highlightOptions(
      weight = 5,
      color = "#666",
      dashArray = "",
      fillOpacity = 0.7,
      bringToFront = TRUE
    ),
    label = ~paste(name, "Average Suicide Rate: ", round(Average_Suicide_Rate, 2)),
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "15px",
      direction = "auto"
    )
  ) %>%
  addLegend(pal = pal, values = ~Average_Suicide_Rate, opacity = 0.7, title = "Average Suicide Rate", position = "bottomright") %>%
  addControl("<strong>Average Suicide Rates by Country</strong>", position = "topright", 
             className = "map-title")  # Add title to the map

# Load the data (change the path to where your file is stored)
suicide_data <- read.csv("/Users/kiran/Documents/GMU/STAT 515/Mid Project/suicide-rates-all.csv")

# Calculate the overall average suicide rate for each year across all countries
yearly_avg_suicide_rate <- suicide_data %>%
  group_by(Year) %>%
  summarise(Average_Suicide_Rate = mean(suscide.rate, na.rm = TRUE))

# Find the year with the highest overall average suicide rate
top_year <- yearly_avg_suicide_rate %>%
  filter(Average_Suicide_Rate == max(Average_Suicide_Rate)) %>%
  pull(Year)

# Filter the data to include only the data for the top year
top_year_data <- suicide_data %>%
  filter(Year == top_year)

# Load world map data
world <- ne_countries(scale = "medium", returnclass = "sf")

# Merge world map data with suicide rate data for the top year
world_data <- merge(world, top_year_data, by.x = "name", by.y = "Country", all.x = TRUE)

# Create color palette for the suicide rates in the top year
pal <- colorNumeric(palette = "YlOrRd", domain = world_data$suscide.rate, na.color = "transparent")

# Create interactive leaflet map
map <- leaflet(world_data) %>%
  addTiles() %>%
  addPolygons(
    fillColor = ~pal(suscide.rate),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "3",
    fillOpacity = 0.7,
    highlight = highlightOptions(
      weight = 5,
      color = "#666",
      dashArray = "",
      fillOpacity = 0.7,
      bringToFront = TRUE
    ),
    label = ~paste(name, "<br> Suicide Rate: ", round(suscide.rate, 2)),
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "15px",
      direction = "auto"
    )
  ) %>%
  addLegend(pal = pal, values = ~suscide.rate, opacity = 0.7, title = paste("Suicide Rate in", top_year), position = "bottomright")%>%
addControl("<strong>Average Suicide Rates of all the ages by Country for the top rated year: 1982</strong>", position = "topright", 
             className = "map-title")  # Add title to the map

# Show the map
map

# Read the data
data <- read_csv(
  "/Users/kiran/Documents/GMU/STAT 515/Mid Project/suicide-rates-all.csv",
  col_types = cols(
    Country = col_character(),
    Code = col_character(),
    Year = col_double(),
    `suscide-rate` = col_double()
  )
)

# Step 1: Calculate the average suicide rate for each year
avg_suicide_by_year <- data %>%
  group_by(Year) %>%
  summarise(Average_suicide_rate = round(mean(`suscide-rate`, na.rm = TRUE), 2), .groups = "drop")

# Step 2: Create the frequency polygon
frequency_polygon <- ggplot(avg_suicide_by_year, aes(x = Year, y = Average_suicide_rate)) +
  geom_line(stat = "identity", color = "blue", size = 1) +  # Line to connect data points
  geom_point(color = "red") +  # Points for each year
  labs(title = "Average Suicide Rates by Year all over the world", 
       x = "Year", 
       y = "Average Suicide Rate per 100,000") +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"), 
    axis.title.x = element_text(face = "bold"), 
    axis.title.y = element_text(face = "bold")
  )

# Convert the frequency polygon to an interactive plot
interactive_frequency_polygon <- ggplotly(frequency_polygon)

# Show the interactive frequency polygon
interactive_frequency_polygon

# Load required libraries
library(ggplot2)
library(dplyr)
library(plotly)
library(readr)  # Ensure you have the readr library to read CSV files

# Read the data
data <- read_csv(
  "/Users/kiran/Documents/GMU/STAT 515/Mid Project/suicide-rates-all.csv",
  col_types = cols(
    Country = col_character(),
    Code = col_character(),
    Year = col_double(),
    `suscide-rate` = col_double()
  )
)

# Step 1: Find top 5 countries with highest average suicide rates
top_5_countries <- data %>%
  group_by(Country) %>%
  summarise(avg_suicide_rate = round(mean(`suscide-rate`, na.rm = TRUE), 2), .groups = "drop") %>%
  top_n(5, wt = avg_suicide_rate) %>%
  arrange(desc(avg_suicide_rate))

# Step 2: Filter the original data to keep only the top 5 countries
data_top_countries <- data %>%
  filter(Country %in% top_5_countries$Country)

# Step 3: Find the top 5 unique years with highest suicide rates across all top countries
top_years <- data_top_countries %>%
  arrange(desc(`suscide-rate`)) %>%
  distinct(Year, .keep_all = TRUE) %>%  # Keep only unique years
  slice_head(n = 5) %>%  # Get top 5 unique years
  pull(Year)  # Extract the years

# Step 4: Filter the data for the top 5 countries and the selected top years
top_5_years_data <- data_top_countries %>%
  filter(Year %in% top_years) %>%
  group_by(Country, Year) %>%
  summarise(`suscide-rate` = round(mean(`suscide-rate`, na.rm = TRUE), 2), .groups = "drop") %>%
  arrange(Country, desc(`suscide-rate`))  # Sort for final presentation

# Step 5: Expand the custom color palette to match the number of unique years
unique_years <- length(unique(top_5_years_data$Year))
color_palette <- colorRampPalette(c("orange", "red"))(unique_years)

# Step 6: Create the plot using ggplot
plot <- ggplot(top_5_years_data, aes(x = Country, y = `suscide-rate`, fill = factor(Year))) +
  geom_bar(stat = "identity", position = "dodge") +
  coord_flip() +
  scale_fill_manual(values = color_palette, name = "Year") +  # Use the custom palette
  labs(title = "Top 5 Years with Highest Suicide Rates in Top 5 Countries", 
       x = "Country", 
       y = "Suicide Rate per 100,000") +
  theme_minimal()

# Step 7: Convert the plot to an interactive plot using plotly
# Use sprintf to format the suicide rates to 2 decimal places in the tooltip
interactive_plot <- ggplotly(plot) %>%
  style(hoverinfo = "text", 
        text = paste("Country: ", top_5_years_data$Country, "<br>",
                     "Year: ", top_5_years_data$Year, "<br>",
                     "Suicide Rate: ", sprintf("%.2f", top_5_years_data$`suscide-rate`)))

# Show the interactive plot
interactive_plot

# Load necessary libraries
library(tidyverse)
library(plotly)
library(rnaturalearth)
library(sf)

# Read the data
# Load necessary libraries
library(tidyverse)
library(plotly)
library(rnaturalearth)
library(sf)

# Read the data
data <- read.csv("/Users/kiran/Downloads/suicide-rates-by-age.csv")

# Clean column names for easier access
colnames(data) <- c("Entity", "Code", "Year", 
                    "Death_rate_15_19", "Death_rate_20_24", "Death_rate_25_29", 
                    "Death_rate_30_34", "Death_rate_35_39", "Death_rate_40_44", 
                    "Death_rate_45_49", "Death_rate_50_54", "Death_rate_55_59", 
                    "Death_rate_60_64", "Death_rate_65_69", "Death_rate_70_74", 
                    "Death_rate_75_79", "Death_rate_80_84", "Death_rate_over_85")

# Filter for the 15-19 age group and calculate the sum of averages across all years for each country
data_summary <- data %>%
  filter(!is.na(Death_rate_15_19)) %>%
  group_by(Entity) %>%
  summarise(Average_suscide_rate = sum(Death_rate_15_19, na.rm = TRUE), .groups = "drop") %>%
  mutate(Average_suscide_rate = round(Average_suscide_rate, 2))  # Round to 2 decimals

# Load the world map using the rnaturalearth package
world <- ne_countries(scale = "medium", returnclass = "sf")

# Join suicide data with the world map
world_data <- world %>%
  left_join(data_summary, by = c("name" = "Entity"))

# Plot the map using ggplot with shades of red
p <- ggplot(world_data) +
  geom_sf(aes(fill = Average_suscide_rate, text = name), color = "white") +
  scale_fill_gradient(low = "#ffcccc", high = "#990000", na.value = "grey50", 
                      name = "Suicide Rate per 100,000") +
  theme_void() +
  labs(title = "Average Suicide Rates for Age 15-19 over the Years")

# Convert ggplot to an interactive plotly map
interactive_map <- ggplotly(p, tooltip = c("text", "fill"))

# Show the interactive map
interactive_map

# Load necessary libraries
library(ggplot2)
library(dplyr)
library(plotly)

# Load the data
data <- read.csv("/Users/kiran/Downloads/suicide-rates-by-age.csv")

# Clean column names for easier access
colnames(data) <- c("Entity", "Code", "Year", 
                    "Death_rate_15_19", "Death_rate_20_24", "Death_rate_25_29", 
                    "Death_rate_30_34", "Death_rate_35_39", "Death_rate_40_44", 
                    "Death_rate_45_49", "Death_rate_50_54", "Death_rate_55_59", 
                    "Death_rate_60_64", "Death_rate_65_69", "Death_rate_70_74", 
                    "Death_rate_75_79", "Death_rate_80_84", "Death_rate_over_85")

# Filter the data for the 15-19 age group and remove missing values
data_filtered <- data %>%
  filter(!is.na(Death_rate_15_19))

# Calculate the average suicide rate for each country across all years
avg_suicide_rate <- data_filtered %>%
  group_by(Entity) %>%
  summarise(suscide_Rate = round(mean(Death_rate_15_19, na.rm = TRUE),2)) %>%
  arrange(desc(suscide_Rate))%>%
  top_n(20, suscide_Rate)



# Create the bar plot with ggplot
bar_plot <- ggplot(avg_suicide_rate, aes(x = reorder(Entity, suscide_Rate), 
                                           y = suscide_Rate, 
                                           fill = suscide_Rate)) +
  geom_bar(stat = "identity") +
  coord_flip() +  # Flip coordinates to make country names readable
  scale_fill_gradient(low = "#ffcccc", high = "#990000") +  # Light red to dark red gradient
  labs(title = "Average Suicide Rate for Age 15-19 (All Years)", 
       x = "Country", 
       y = "Average Suicide Rate per 100,000 Population") +
  theme_minimal() +
  theme(axis.text.y = element_text(angle = 0, hjust = 1, size = 8)) +  # Adjust text angle and size
  theme(plot.margin = margin(10, 10, 10, 40))  # Adjust margins

# Convert to an interactive plot with plotly
interactive_plot <- ggplotly(bar_plot, tooltip = c("suscide_Rate"))

# Show the interactive plot
interactive_plot